{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GJ4PHVIFOQYNDYJLGQOPYHOWU2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82bae6067f23542825aeaa7fb4aa7a4bcd0d4fc9a685abffdeee57ce70cd974a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T14:20:01Z","title_canon_sha256":"4353531b7b5d4c541e254b401525e7e55644f27d51720f627e40edc00c01ec43"},"schema_version":"1.0","source":{"id":"1903.02930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02930","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02930v1","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02930","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"GJ4PHVIFOQYN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GJ4PHVIFOQYNDYJL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GJ4PHVIF","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:10c24ec9fc30b5d1ba0443cd4d873b3c3c0fe488e016dc96859b7102ab96ad3f","target":"graph","created_at":"2026-05-17T23:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our models on data that is two orders-of-magnitude bigger than datasets used in prior work. We perform a thorough exploration of model architectures for combining visual and text features. Our experiments on two corpora (YouCookII and 20bn-something-something-v2) show that the best performing architecture consists of middle fusion of visual and text features, yieldin","authors_text":"Antonios Anastasopoulos, Hank Liao, Shankar Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T14:20:01Z","title":"Neural Language Modeling with Visual Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02930","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7630df9aa41e8b822dd62baa8cdc9908f52bd1bffa2672e426318e332510924b","target":"record","created_at":"2026-05-17T23:51:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82bae6067f23542825aeaa7fb4aa7a4bcd0d4fc9a685abffdeee57ce70cd974a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-07T14:20:01Z","title_canon_sha256":"4353531b7b5d4c541e254b401525e7e55644f27d51720f627e40edc00c01ec43"},"schema_version":"1.0","source":{"id":"1903.02930","kind":"arxiv","version":1}},"canonical_sha256":"3278f3d5057430d1e12b341cfc1dd6a698d22e726444853c4a3dbb47b3f09e66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3278f3d5057430d1e12b341cfc1dd6a698d22e726444853c4a3dbb47b3f09e66","first_computed_at":"2026-05-17T23:51:50.707162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:50.707162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gyEOJ7UaD2SHDOYiscw0i+uJhBDgeA3QUT0DOGwMsJDMGxFTzlSu3ChDoZaxq/c1j3PL+GSVAmWBxl2A66qfDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:50.707877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.02930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7630df9aa41e8b822dd62baa8cdc9908f52bd1bffa2672e426318e332510924b","sha256:10c24ec9fc30b5d1ba0443cd4d873b3c3c0fe488e016dc96859b7102ab96ad3f"],"state_sha256":"d561955577c2a35f1c85316e759c1694ea026b25f304e501b63b9c209a54e018"}